System and method for identifying contextual information in streaming content

Abstract

Systems and methods for identifying contextual information in streams of content being delivered by streaming platforms are discussed. In response to a request for additional content, streaming content is examined for relevant contextual information that occurs close in time to upcoming scheduled breaks. The identified contextual information may be used to insert additional content in the stream of content. Techniques for determining and applying a ratio for the handling of requests amongst multiple streaming platforms and a video ingestion and processing framework are also discussed.

We claim: 
     
         1 . A computing device-implemented method to identify contextual information in a stream of content being delivered by a streaming platform, the computing device including at least one processor, the method comprising:
 receiving, at a server over a network, a request for additional content for insertion into a stream of content being delivered by a streaming platform to a user device;   downloading a stream of content corresponding to an identified program in the stream of content being delivered by the streaming platform;   identifying a plurality of upcoming media file segments in the stream of content for the identified program;   identifying contextual information in one or more of the plurality of upcoming media file segments;   storing a record of the identified contextual information that indicates a time of appearance of the contextual information in the stream of content;   identifying scheduled breaks in the plurality of upcoming media file segments;   mapping a time window of a pre-determined duration starting at a time of the request against the identified scheduled breaks in the plurality of upcoming media file segments;   determining whether stored contextual information exists for the stream of content for an upcoming break within the time window; and   delivering or facilitating the delivery of additional content to the requesting streaming platform using the contextual information to satisfy the request for additional content when the stored contextual information exists within the time window.   
     
     
         2 . The method of  claim 1 , wherein the plurality of upcoming media file segments in the stream of content for the identified program are identified by examining a manifest or playlist for the identified program. 
     
     
         3 . The method of  claim 1 , wherein the contextual information is identified using a speech-to-text module. 
     
     
         4 . The method of  claim 1 , wherein the contextual information is identified using a video-to-text module. 
     
     
         5 . The method of  claim 1 , wherein the contextual information is identified using a natural language processing module. 
     
     
         6 . The method of  claim 1 , wherein the contextual information is identified using an object recognition module. 
     
     
         7 . The method of  claim 1 , wherein the contextual information is identified using a music recognition module. 
     
     
         8 . The method of  claim 1 , wherein the contextual information is identified using one or more of machine learning or artificial intelligence. 
     
     
         9 . The method of  claim 1 , wherein at least one of the media file segments corresponds to a scene in the identified program or a pre-determined length of time in the identified program. 
     
     
         10 . The method of  claim 1 , wherein the additional content is a public service announcement or nature scene. 
     
     
         11 . The method of  claim 1  wherein the additional content is additional information associated with the identified program. 
     
     
         12 . The method of  claim 1  wherein the additional content is an advertisement. 
     
     
         13 . The method of  claim 1 , further comprising:
 determining whether the stream of content is the same as a previously analyzed stream of content prior to downloading the stream of content corresponding to the identified program, the determining comparing a manifest for the stream of content corresponding to the identified program with a manifest for the previously analyzed stream, wherein the stream of content corresponding to the identified program is downloaded when the manifest comparison indicates the streams of content are not the same.   
     
     
         14 . The method of  claim 1 , further comprising:
 determining whether the stream of content is the same as a previously analyzed stream of content prior to identifying contextual information in one or more of the plurality of upcoming media file segments, the determining:
 comparing content of a plurality of upcoming media file segments for the stream of content corresponding to the identified program with file segments for the previously analyzed stream, and 
 identifying contextual information for the stream of content corresponding to the identified program when the comparison indicates the streams of content are not the same. 
   
     
     
         15 . The method of  claim 1 , further comprising:
 establishing a pre-determined ratio threshold for handling all streaming platform requests for additional content using contextual information within a pre-determined period of time, the ratio indicating a threshold for a number of requests from a specific streaming platform in view of a total number of all streaming platform requests;   identifying the specific streaming platform delivering the stream of content;   determining a number of requests for additional content using contextual information received for the specific streaming platform within the pre-determined period of time;   comparing the number of requests to the pre-determined ratio threshold for all streaming platform requests within the pre-determined period of time; and   delivering or facilitating the delivery of additional content to the requesting streaming platform using the contextual information to satisfy the request for additional content when the number of requests for the specific streaming platform is below the ratio threshold.   
     
     
         16 . The method of  claim 15 , wherein the ratio threshold is static. 
     
     
         17 . The method of  claim 15 , wherein the ratio threshold is dynamic and programmatically adjusts based on a monitored number of requests received. 
     
     
         18 . The method of  claim 1 , further comprising:
 providing a framework for ingesting and processing Electronic Program Guide (EPG) information, the framework abstracting a plurality of attributes common to a plurality of EPG providers.   
     
     
         19 . The method of  claim 14 , wherein the framework includes one or more generalized tools for detecting ad breaks in video content. 
     
     
         20 . A non-transitory medium holding computing device-executable instructions for identifying contextual information in a stream of content being delivered by a streaming platform, the computing device including at least one processor, the instructions when executed causing at least one computing device to:
 receive, at a server over a network, a request for additional content for insertion into a stream of content being delivered by a streaming platform to a user device;   download a stream of content corresponding to an identified program in the stream of content being delivered by the streaming platform;   identify a plurality of upcoming media file segments in the stream of content for the identified program;   identify contextual information in one or more of the plurality of upcoming media file segments;   store a record of the identified contextual information that indicates a time of appearance of the contextual information in the stream of content;   identify scheduled breaks in the plurality of upcoming media file segments;   map a time window of a pre-determined duration starting at a time of the request against the identified scheduled breaks in the plurality of upcoming media file segments;   determine whether stored contextual information exists for the stream of content for an upcoming break within the time window; and   deliver or facilitate the delivery of additional content to the requesting streaming platform using the contextual information to satisfy the request for additional content when the stored contextual information exists within the time window.   
     
     
         21 . The medium of  claim 20 , wherein the plurality of upcoming media file segments in the stream of content for the identified program are identified by examining a manifest or playlist for the identified program. 
     
     
         22 . The medium of  claim 20 , wherein the contextual information is identified using a speech-to-text module. 
     
     
         23 . The medium of  claim 20  wherein the contextual information is identified using a video-to-text module. 
     
     
         24 . The medium of  claim 20 , wherein the contextual information is identified using a natural language processing module. 
     
     
         25 . The medium of  claim 20 , wherein the contextual information is identified using an object recognition module. 
     
     
         26 . The medium of  claim 20 , wherein the contextual information is identified using a music recognition module. 
     
     
         27 . The medium of  claim 20 , wherein the contextual information is identified using one or more of machine learning or artificial intelligence. 
     
     
         28 . The medium of  claim 20 , wherein at least one of the media file segments corresponds to a scene in the identified program or a pre-determined length of time in the identified program. 
     
     
         29 . The medium of  claim 20 , wherein the additional content is a public service announcement or nature scene. 
     
     
         30 . The medium of  claim 20 , wherein the additional content is additional information associated with the identified program. 
     
     
         31 . The medium of  claim 20 , wherein the additional content is an advertisement. 
     
     
         32 . The medium of  claim 20 , wherein the instructions when executed further cause the at least one computing device to:
 determine whether the stream of content is the same as a previously analyzed stream of content prior to downloading the stream of content corresponding to the identified program, the determining comparing a manifest for the stream of content corresponding to the identified program with a manifest for the previously analyzed stream, wherein the stream of content corresponding to the identified program is downloaded when the manifest comparison indicates the streams of content are not the same.   
     
     
         33 . The medium of  claim 20 , wherein the instructions when executed further cause the at least one computing device to:
 determine whether the stream of content is the same as a previously analyzed stream of content prior to identifying contextual information in one or more of the plurality of upcoming media file segments, the determining:
 comparing content of a plurality of upcoming media file segments for the stream of content corresponding to the identified program with file segments for the previously analyzed stream, and 
 identifying contextual information for the stream of content corresponding to the identified program when the comparison indicates the streams of content are not the same. 
   
     
     
         34 . The medium of  claim 20 , wherein the instructions when executed further cause the at least one computing device to:
 establish a pre-determined ratio threshold for handling all streaming platform requests for additional content using contextual information within a pre-determined period of time, the ratio indicating a threshold for a number of requests from a specific streaming platform in view of a total number of all streaming platform requests;   identify the specific streaming platform delivering the stream of content;   determine a number of requests for additional content using contextual information received for the specific streaming platform within the pre-determined period of time;   compare the number of requests to the pre-determined ratio threshold for all streaming platform requests within the pre-determined period of time; and   deliver or facilitate the delivery of additional content to the requesting streaming platform using the contextual information to satisfy the request for additional content when the number of requests for the specific streaming platform is below the ratio threshold.   
     
     
         35 . The medium of  claim 34 , wherein the ratio threshold is static. 
     
     
         36 . The medium of  claim 34 , wherein the ratio threshold is dynamic and programmatically adjusts based on a monitored number of requests received. 
     
     
         37 . The medium of  claim 20 , wherein the instructions when executed further cause the at least one computing device to:
 provide a framework for ingesting and processing Electronic Program Guide (EPG) information, the framework abstracting a plurality of attributes common to a plurality of EPG providers.   
     
     
         38 . The medium of  claim 37 , wherein the framework includes one or more generalized tools for detecting ad breaks in video content. 
     
     
         39 . A system for identifying contextual information in a stream of content being delivered by a streaming platform, comprising:
 one or more network accessible storage locations holding additional content;   a network accessible computing device equipped with at least one processor, the network-accessible computing device including an analysis module, the analysis module when executed by the at least one processor configured to:
 receive a request for additional content for insertion into a stream of content being delivered by a streaming platform to a user device; 
 download a stream of content corresponding to an identified program in the stream of content being delivered by the streaming platform; 
 identify a plurality of upcoming media file segments in the stream of content for the identified program; 
 identify contextual information in one or more of the plurality of upcoming media file segments; 
 store a record of the identified contextual information that indicates a time of appearance of the contextual information in the stream of content; 
 identify scheduled breaks in the plurality of upcoming media file segments; 
 map a time window of a pre-determined duration starting at a time of the request against the identified scheduled breaks in the plurality of upcoming media file segments; 
 determine whether stored contextual information exists for the stream of content for an upcoming break within the time window; and 
 deliver or facilitate the delivery of additional content from the one or more storage locations to the requesting streaming platform using the contextual information to satisfy the request for additional content when the stored contextual information exists within the time window. 
   
     
     
         40 . The system of  claim 39 , wherein the contextual information is identified using one or more of a speech-to-text module, a video-to-text module, a natural language processing module, an object recognition module or a music recognition module. 
     
     
         41 . The system of  claim 40 , wherein the contextual information is identified using one or more of machine learning or artificial intelligence.